This article describes CART (Classification and Regression Trees)—an interesting and often powerful nonparametric alternative to parametric methods in modeling. The algorithm and accompanying software is described and contrasted to CHAID (Chi-Square Automatic Interaction Detection). Finally, a case study showing CART's application in response modeling is discussed.
Get full access to this article
View all access options for this article.
References
1.
BreimanL.FriedmanJ.OlshenR.StoneC.Classification and Regression Trees1984WadsworthBelmont, CA
2.
BreimanL.FriedmanJ.Comment on “Tree-Structured Classification via Generalized Discriminant Analysis” Journal of the American Statistical Association834031988725–727
3.
MagidsonJ.Improved Statistical Techniques for Response ModelingJournal of Direct Marketing2419886–18
4.
Panel on Discriminant Analysis, Classification, and Clustering, Committee on Applied and Theoretical Statistics of the Board on Mathematical Sciences, National Research CouncilDiscriminant Analysis and ClusteringStatistical Science41198934–69
5.
PerreaultW.JrCHAID: A Computer Program for Market Segmentation1986Perreault and AssociatesChapel Hill, NC
